Lookahead adversarial learning for near real-time semantic segmentation

Hadi Jamali-Rad, Attila Szabó

Research output: Contribution to journalArticleScientificpeer-review

2 Downloads (Pure)

Abstract

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation quality by enforcing higher-level pixel correlations and structural information. However, state-of-the-art semantic segmentation models cannot be easily plugged into an adversarial setting because they are not designed to accommodate convergence and stability issues in adversarial networks. We bridge this gap by building a conditional adversarial network with a state-of-the-art segmentation model (DeepLabv3+) at its core. To battle the stability issues, we introduce a novel lookahead adversarial learning (LoAd) approach with an embedded label map aggregation module. We focus on semantic segmentation models that run fast at inference for near real-time field applications. Through extensive experimentation, we demonstrate that the proposed solution can alleviate divergence issues in an adversarial semantic segmentation setting and results in considerable performance improvements (+5% in some classes) on the baseline for three standard datasets.

Original languageEnglish
Article number103271
Number of pages17
JournalComputer Vision and Image Understanding
Volume212
DOIs
Publication statusPublished - 2021

Keywords

  • Computer vision
  • Conditional adversarial training
  • Deep learning
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'Lookahead adversarial learning for near real-time semantic segmentation'. Together they form a unique fingerprint.

Cite this